A Sentence Similarity Estimation Method Based on Improved Siamese Network

In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design our model based on the Siamese network using deep Long Short-Term Memory (LSTM) Network. And we add the special attention mechanism to let the model give different words different attention while modeling sentences. The fully-connected layer is proposed to measure the complex sentence representations. Our results show that the accuracy is better than the baseline in 2016. Furthermore, it is showed that the model has the ability to model the sequence order, distribute reasonable attention and extract meanings of a sentence in different dimensions.

Information mining and similarity computation for semi-/un-structured sentences from the social data

In recent years,with the development of the social Internet of Things(IoT),all kinds of data accumulated on the network.These data,which contain a lot of social information and opinions.However,these data are rarely fully analyzed,which is a major obstacle to the intelligent development of the social IoT.In this paper,we propose a sentence similarity analysis model to analyze the similarity in people’s opinions on hot topics in social media and news pages.Most of these data are unstructured or semi-structured sentences,so the accuracy of sentence similarity analysis largely determines the model’s performance.For the purpose of improving accuracy,we propose a novel method of sentence similarity computation to extract the syntactic and semantic information of the semi-structured and unstructured sentences.We mainly consider the subjects,predicates and objects of sentence pairs and use Stanford Parser to classify the dependency relation triples to calculate the syntactic and semantic similarity between two sentences.Finally,we verify the performance of the model with the Microsoft Research Paraphrase Corpus(MRPC),which consists of 4076 pairs of training sentences and 1725 pairs of test sentences,and most of the data came from the news of social data.Extensive simulations demonstrate that our method outperforms other state-of-the-art methods regarding the correlation coefficient and the mean deviation.

A New Method for Calculating Similarity between Sentences and Application on Automatic Abstracting

Sentence similarity computing plays an important role in machine question-answering systems, machine-translation systems, information retrieval and automatic abstracting systems. This article firstly sums up several methods for calculating similarity between sentences, and brings out a new method which takes all factors into consideration including critical words, semantic information, sentential form and sen-tence length. And on this basis, a automatic abstracting system based on LexRank algorithm is implemented. We made several improvements in both sentence weight computing and redundancy resolution. The system described in this article could deal with single or multi-document summarization both in English and Chinese. With evaluations on two corpuses, our system could produce better summaries to a certain degree. We also show that our system is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents. And in the end, existing problem and the developing trend of automatic summariza-tion technology are discussed.

Sentence Similarity Measurement with Convolutional Neural Networks Using Semantic and Syntactic Features

Calculating the semantic similarity of two sentences is an extremely challenging problem.We propose a solution based on convolutional neural networks(CNN)using semantic and syntactic features of sentences.The similarity score between two sentences is computed as follows.First,given a sentence,two matrices are constructed accordingly,which are called the syntax model input matrix and the semantic model input matrix;one records some syntax features,and the other records some semantic features.By experimenting with different arrangements of representing the syntactic and semantic features of the sentences in the matrices,we adopt the most effective way of constructing the matrices.Second,these two matrices are given to two neural networks,which are called the sentence model and the semantic model,respectively.The convolution process of the neural networks of the two models is carried out in multiple perspectives.The outputs of the two models are combined as a vector,which is the representation of the sentence.Third,given the representation vectors of two sentences,the similarity score of these representations is computed by a layer in the CNN.Experiment results show that our algorithm(SSCNN)surpasses the performance MPCPP,which noticeably the best recent work of using CNN for sentence similarity computation.Comparing with MPCNN,the convolution computation in SSCNN is considerably simpler.Based on the results of this work,we suggest that by further utilization of semantic and syntactic features,the performance of sentence similarity measurements has considerable potentials to be improved in the future.

Hepatic Angiomyolipoma Demonstrating Similar Imaging Characteristics as Hepatocellular Carcinoma: One Case Report

Angiomyolipoma （AML） is a benign mesenchymal tumor that has been frequently reported in the kidney but rarely in the liver. AML is composed of fat, vascular, and smooth muscle elements. Because the proportion of the constituents composed of AML are varied, hepatic AML may be clinically, radiologically and morphologically difficult to distinguish from hepatocellular carcinoma （HCC） or other hepatic lesions. Here we report a case with pathologically confirmed hepatic AML who was previously diagnosed as HCC based on imaging examinations.

AFDES中基于Case推理方法的研究

本文对“汽车故障诊断专家系统(AFDES)”中的基于Case推理方法进行了研究,介绍了不确定知识的事例表达、事例的存储和检索,提出了事例的相似度计算算法和基于事例推理算法。

Case-Based Reasoning(CBR) Model for Ultra-Fast Cooling in Plate Mill

New generation thermo-mechanical control process（TMCP） based on ultra-fast cooling is being widely adopted in plate mill to product high-performance steel material at low cost. Ultra-fast cooling system is complex because of optimizing the temperature control error generated by heat transfer mathematical model and process parameters. In order to simplify the system and improve the temperature control precision in ultra-fast cooling process, several existing models of case-based reasoning（CBR） model are reviewed. Combining with ultra-fast cooling process, a developed R5 CBR model is proposed, which mainly improves the case representation, similarity relation and retrieval module. Certainty factor is defined in semantics memory unit of plate case which provides not only internal data reliability but also product performance reliability. Similarity relation is improved by defined power index similarity membership function. Retrieval process is simplified and retrieval efficiency is improved apparently by windmill retrieval algorithm. The proposed CBR model is used for predicting the case of cooling strategy and its capability is superior to traditional process model. In order to perform comprehensive investigations on ultra-fast cooling process, different steel plates are considered for the experiment. The validation experiment and industrial production of proposed CBR model are carried out, which demonstrated that finish cooling temperature（FCT） error is controlled within±25℃ and quality rate of product is more than 97%. The proposed CBR model can simplify ultra-fast cooling system and give quality performance for steel product.

Case-based retrieval approach for machining fixture design utilizingontology

In order to develop an intelligent case-based reasoning （CBR） system to reuse fixture de- sign knowledge, ontology technology was integrated in CBR system by semantic annotation of fixture design case. Domain ontology of fixture design was constructed; concepts and relations were de- fined and represented. The 2-level similarity evaluation approach of domain ontology was presented. The concept similarity of cases was calculated as the first grade case retrieval. Numerical measure- ment was the second grade case retrieval, which adopted various methods to calculate different types of attribute values. The problem of similarity measurement of fixture design case was resolved. Pro- totype system based on the proposed method was illustrated and the retrieval approach was proved to be efficient.

Design System of the Two-step Gear Reducer on Case-based Reasoning

The design of the two-step gear reducer is a tedious and time-consuming process. For the purpose of improving the efficiency and intelligence of design process, case-based reasoning（CBR） technology was applied to the design of the two-step gear reducer. Firstly, the current design method for the two-step gear reducer was analyzed and the principle of CBR was described. Secondly, according to the characteristics of the reducer, three key technologies of CBR were studied and the corresponding methods were provided, which are as follows： （a） an object-oriented knowledge representation method, （b） a retrieval method combining the nearest neighbor with the induction indexing, and （c） a case adaptation algorithm combining the revision based on rule with artificial revision. Also, for the purpose of improving the credibility of case retrieval, a new method for determining the weights of characteristics and a similarity formula were presented, which is a combinatorial weighting method with the analytic hierarchy process（AHP） and roughness set theory. Lastly, according to the above analytic results, a design system of the two-step gear reducer on CBR was developed by VC＋＋, UG and Access 2003. A new method for the design of the two-step gear reducer is provided in this study. If the foregoing developed system is applied to design the two-step gear reducer, design efficiency is improved, which enables the designer to release from the tedious design process of the gear reducer so as to put more efforts on innovative design. The study result fully reflects the feasibility and validity of CBR technology in the process of the design of the mechanical parts.

A Retrieval Matching Method Based Case Learning for 3D Model

The similarity metric in traditional content based 3D model retrieval method mainly refers the distance metric algorithm used in 2D image retrieval. But this method will limit the matching breadth. This paper proposes a new retrieval matching method based on case learning to enlarge the retrieval matching scope. In this method, the shortest path in Graph theory is used to analyze the similarity how the nodes on the path between query model and matched model effect. Then, the label propagation method and k nearest-neighbor method based on case learning is studied and used to improve the retrieval efficiency based on the existing feature extraction.

DESIGN TECHNOLOGY FOR INJECTION MOLD PARTING SURFACE BASED ON CASES AND KNOWLEDGE

On the basis of the comprehensive analysis about the automatic generation of the injection mold parting surface, the parting surface design method which introduces knowledge and case-based reasoning （CBR） into the computer-aided design is described by combining with the actual characteristic in injection mold design, and the design process of case-based reasoning method is also given. A case library including the information of parting surface is built with the index of main shape features, The automatic design of the mold parting surface is realized combined with the forward-reasoning method and the similarity solution procedure. The rule knowledge library is also founded including the knowledge, principles and experiences for parting surface design. An example is used to show the validity of the method, and the quality and the efficiency of the mold design are improved.

Case Retrieval Method of Multi-parameter for Customized Product

The CBR (Case-Based Reasoning) usually is been used to accomplish customized products by variant design or reusable design.In the CBR,retrieve is very important.A simple case retrieval method is been brought forward to retrieve a opti- mal prototype based on using inputted multi-parameters,it can be programmed easily.An example has been proved this method can find optimal prototype for new design task efficiently.

基于案例推理的隧道洞门智能设计方法研究

为将以往隧道案例的经验应用到新建隧道设计中,以解决传统设计方法工作量大且效率低下的问题,提出基于案例推理的隧道洞门智能设计方法。结合隧道洞门工程特点,选取影响洞门设计的主要因素,将影响因素划分为12个属性单元来表征工程案例,运用三角模糊数的层次赋权计算方法对各属性单元权重进行赋值,借助相似度理论建立隧道洞门设计方案相似决策模型。基于GIS技术开发了隧道洞门工程案例库,实现对既有工程的存储管理,同时利用SQL查询语言及Python计算脚本实现案例的属性特征值计算与最相似匹配,进一步修正后可实现隧道洞门修建方案的设计决策。以某山区隧道为例对智能设计方法进行验证,结果表明:根据属性单元特征值计算结果,在案例库中比选得出与拟建隧道相似度最高的既有工程为凤凰山隧道,且相似度为0.707。因此,设定阈值为0.7时能加快案例库的检索速率与匹配准确率,该方法吸取了既有工程案例的经验,能应用于隧道洞门施工方案的决策设计,可供今后隧道洞门方案的智能化设计参考。

Application of Case-Based Reasoning to Intelligent Support System for Coordinating Land Conflicts

To establish the institutional mechanism for land conflict coordination in China, a case-based reasomng system is developed as an intelligent support and effective manner to resolve such issues. The establishment of the case library is discussed, previous land conflict cases are archived in a structural representation format for retrieval, and the similarity algorithm is adopted to compare the case features. Group tests show a good classification performance, which reveals that the system is feasible.

基于路径相似表与个体迁移策略的多路径覆盖测试

将遗传算法用于多路径覆盖测试中是个研究热点,在新旧种群迭代过程中,旧种群中可能包含其他子种群的优秀个体,这部分个体未被充分利用,造成资源浪费;同时,种群中的个体数会远大于可达路径数,而每个个体都会经过某一条可达路径,这样会有多个个体经过同一条路径,导致重复计算个体与目标路径的相似度。基于此,提出结合路径相似表与个体迁移的多路径覆盖测试方法以提高测试效率。通过路径相似表存储已计算得到的路径相似度值,避免该值被重复计算,减少测试时间。在进化过程中,将个体路径与其他目标路径进行比较,若相似度达到阈值,则将此优秀个体迁移至该路径对应的子种群中,提高个体利用率并减少进化代数。由实验可知,该方法与其他六种同类经典方法在八个程序上的平均生成时间降低最高达44.64%,最低为2.64%,平均进化代数降低最高达35.08%,最低为6.13%,故该方法有效地提高了测试效率。

考虑舆情演化态势影响的突发事件两阶段应急案例检索方法

针对突发事件衍生的舆情信息及其演化态势影响应急处置决策的问题,本文提出一种考虑舆情演化态势影响的突发事件两阶段应急案例检索方法。首先,通过计算舆情信息热度值,判断舆情演化态势的影响程度,并确定案例检索阶段;其次,通过融入决策者风险感知偏好,计算事件属性及事件的相似度,并构建第一阶段案例检索过程;在此基础上,通过计算和集结舆情信息属性及舆情信息的相似度,得到案例的综合相似度,并构建第二阶段案例检索过程;最后,通过案例应用和方法对比验证了所提方法的可行性及有效性。结果表明,所提方法不仅能够反映决策者风险感知偏好在应急案例检索中的重要作用,还能够体现事件衍生的舆情信息及其演化态势对决策结果的影响。

推定在涉正当防卫案件中的运用

在司法实践中一些法院办理涉正当防卫案件时常常援引存疑有利被告原则,对证据不充分的不法侵害事实进行推定。这种做法不符合证据法上推定的运用规则,是对推定规则的误解与误用。运用推定必须有明确的基础事实并允许反驳,而不能以一条抽象的难以反驳的存疑有利被告原则作为基础事实。在涉正当防卫案件中,不法侵害事实难以查清往往成为此类案件事实不清的常态。为破解涉正当防卫案件中不法侵害事实难以证明的难题,推定不失为一条可行的路径。司法实践案例反映,相似事实相互之间具有高度的内在关联性,可以在涉正当防卫案件中作为推定不法侵害事实的基础事实。

基于样本对纠正对比学习的问句相似性判别

为解决对比学习在难例问句的相似性判别上准确性不高的问题,提出一种基于样本对纠正对比学习的问句对相似性判别方法。利用预训练模型与双向LSTM结合进行捕获语义特征;采用自注意力机制关注关键信息并利用平均池化策略压缩特征构建句向量;引入样本对对比学习并结合标签误差设计带有惩罚项的对比损失函数,纠正难例相似度得分,增强语义空间的可分离性。实验结果表明,该方法与基线模型相比在问句相似性判别上获得了更好的F1值以及准确率。

柳宝诒与吴鞠通治疗痢疾病案异同研究

目的 分析柳宝诒和吴鞠通治疗痢疾医案的异同,探索2位医家治疗痢疾的用药规律。方法 以《柳宝诒医论医案》和《吴鞠通医案》中治疗痢疾的医案为研究对象,采用Excel2010软件统计用药频次、功效分类等,分析其用药规律、病机治法的异同。结果 柳宝诒治疗痢疾以理气药、止血药、补气药、利水渗湿药为主,高频药物为木香、白术、枳壳、桔梗、砂仁等,吴鞠通治疗痢疾多用清热药、理气药、补血药、利水渗湿药,高频药物为黄芩、白芍、木香、黄连、神曲等。结论 柳宝诒和吴鞠通对痢疾的病因病机认识基本相同,吴鞠通治疗痢疾强调初痢以祛邪为主,多用清热药和理气药,久痢有虚实之分,以攻补兼施、扶助正气为主。柳宝诒在痢疾病机认识上创新性提出“宿垢”观点,治疗上提出“疏化”之法。

论“人民法院案例库”应用中的案件事实相似性判断

案件事实相似性判断是案例库应用中的重要基础性问题。案件事实相似性判断与裁判者视角立场相关、与法律争点交织、与案件事实相异性辨析相随,呈现复杂面相。实现案件事实相似性判断的客观定型需要遵循将案件事实区分为构成要件事实和非构成要件事实的路径。同时,应当重视价值评价的多元和复杂,通过将价值评价聚焦于立法精神实现客观化。当前案例库应用中存在案例应用动力不强、案例数量不足、案例应用目标不明、裁判文书说理欠缺等问题。为此,应当提升案例库应用认识自觉和方法指引;通过检察加入、信息化应用等方式加大案例资源供给;在案例库中试行标附文书,实现办案过程全景展现;同时建立效力异议等制度,强化推进案例库应用。